A Cheap and Dirty Cross-Lingual Linking Service in the Cloud

Christian Chiarcos, Gilles Sérasset


Abstract
In this paper, we describe the application of Linguistic Linked Open Data (LLOD) technology for dynamic cross-lingual querying on demand. Whereas most related research is focusing on providing a static linking, i.e., cross-lingual inference, and then storing the resulting links, we demonstrate the application of the federation capabilities of SPARQL to perform lexical linking on the fly. In the end, we provide a baseline functionality that uses the connection of two web services – a SPARQL end point for multilingual lexical data and another SPARQL end point for querying an English language knowledge graph – in order to perform querying an English language knowledge graph using foreign language labels. We argue that, for low-resource languages where substantial native knowledge graphs are lacking, this functionality can be used to lower the language barrier by allowing to formulate cross-linguistically applicable queries mediated by a multilingual dictionary.
Anthology ID:
2022.ldl-1.7
Volume:
Proceedings of the 8th Workshop on Linked Data in Linguistics within the 13th Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Thierry Declerck, John P. McCrae, Elena Montiel, Christian Chiarcos, Maxim Ionov
Venue:
LDL
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
52–60
Language:
URL:
https://aclanthology.org/2022.ldl-1.7
DOI:
Bibkey:
Cite (ACL):
Christian Chiarcos and Gilles Sérasset. 2022. A Cheap and Dirty Cross-Lingual Linking Service in the Cloud. In Proceedings of the 8th Workshop on Linked Data in Linguistics within the 13th Language Resources and Evaluation Conference, pages 52–60, Marseille, France. European Language Resources Association.
Cite (Informal):
A Cheap and Dirty Cross-Lingual Linking Service in the Cloud (Chiarcos & Sérasset, LDL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.ldl-1.7.pdf